Job description :

In this role, you'll be responsible for building machine-learning-based systems and conducting data analysis to improve the quality of our large geospatial datasets. You'll be developing NLP models to extract information, using outlier detection to identify anomalies, and applying data science methods to quantify the quality of our data. You will take part in the development, integration, productionisation, and deployment of the models at scale, which would require a good combination of data science and software development.

Responsibilities :

- Development of machine learning models

- Building and maintaining software development solutions

- Provide insights by applying data science methods

- Take ownership of delivering features and improvements on time

Must-have Qualifications :

- 4 years' experience

- Senior data scientist preferable with knowledge of NLP

- Strong programming skills and extensive experience with Python

- Professional experience working with LLMs, transformers, and open-source models from Hugging Face

- Professional experience working with machine learning and data science, such as classification, feature engineering, clustering, anomaly detection, and neural networks

- Knowledgeable in classic machine learning algorithms (SVM, Random Forest, Naive Bayes, KNN, etc.).

- Experience using deep learning libraries and platforms, such as PyTorch

- Experience with frameworks such as Scikit-learn, NumPy, Pandas, and Polars

- Excellent analytical and problem-solving skills

- Excellent oral and written communication skills

Extra Merit Qualifications :

- Knowledge in at least one of the following : NLP, information retrieval, data mining

- Ability to do statistical modeling and build predictive models

- Programming skills and experience with Scala and/or Java